Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "dense",
+    "dense_4h_to_h",
     "dense_h_to_4h",
-    "dense_4h_to_h"
+    "dense",
+    "query_key_value"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e454f0e46ac0f231ed99c81636f5c4ca80d6ce6a6808dddeba969a8fe35fb68
+oid sha256:a440c384a28db3746ab5cbb3fdac4d314d14a3a05683d2c94c1d13d0cecdf307
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26db2e69c639eb90b19e758eccdedd042b3848b946ee7cdd7db2e88ff6870eb
+oid sha256:60a5fe63ef4d8541aafffcf77194c8d3e5418f35e643d28cdb3fecbc1bd26d18
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97b60998d53c1d797db53e375383a7d6d6df4606d2b68d39abea77130b5c637
+oid sha256:68a99e76e9e47417219f8179b23e11de131005a80a8a0f68835b1c9c0a9a539c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00046425255338904364,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0060352831940575676,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.00046425255338904364,
       "eval_loss": 4.059295177459717,
-      "eval_runtime": 20.3274,
-      "eval_samples_per_second": 44.62,
-      "eval_steps_per_second": 22.334,
+      "eval_runtime": 20.2414,
+      "eval_samples_per_second": 44.809,
+      "eval_steps_per_second": 22.429,
       "step": 1
+    },
+    {
+      "epoch": 0.002321262766945218,
+      "grad_norm": 113.8918228149414,
+      "learning_rate": 5e-05,
+      "loss": 18.5564,
+      "step": 5
+    },
+    {
+      "epoch": 0.004642525533890436,
+      "grad_norm": 107.09974670410156,
+      "learning_rate": 0.0001,
+      "loss": 16.0422,
+      "step": 10
+    },
+    {
+      "epoch": 0.004642525533890436,
+      "eval_loss": 3.889435291290283,
+      "eval_runtime": 18.1949,
+      "eval_samples_per_second": 49.849,
+      "eval_steps_per_second": 24.952,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 8772856578048.0,
+  "total_flos": 114047135514624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f55b48016f62219de951360391d52b2768f7ab318f845a8233fb89221f0bf6
+oid sha256:c9b62e88ad451a5dbe6f4f702a3e1c388b2bb4b64cf30e1b280622d0dec0690c
 size 6776